© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23540
    Prev
    Next
    INDEX
    Explanations

    Seattle or Tacoma, Washington

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĤ³
    -0.13
    常å·ŀ
    -0.11
    æ·®å®ī
    -0.10
    宿è¿ģ
    -0.10
    临æ²Ĥ
    -0.10
    æ±Łèĭıçľģ
    -0.10
    笪
    -0.09
    æ±Łèĭı
    -0.09
    天津å¸Ĥ
    -0.09
    _states
    -0.09
    POSITIVE LOGITS
    æĪIJéĥ½
    0.22
     Seattle
    0.18
    绵éĺ³
    0.18
    éĤĽ
    0.18
    èľĢ
    0.17
    åĽĽå·Ŀçľģ
    0.17
    æĪIJéĥ½å¸Ĥ
    0.17
    Seattle
    0.17
     Tacoma
    0.16
    å²·
    0.16
    Activations Density 0.585%

    No Known Activations